Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions related to company accountability and corporate behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    but then or yet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     demais
    -0.51
     definitivamente
    -0.47
     memang
    -0.47
    Definitely
    -0.44
     definitely
    -0.44
     давно
    -0.44
     действительно
    -0.43
    truly
    -0.42
     echt
    -0.42
     generell
    -0.42
    POSITIVE LOGITS
     somehow
    0.79
    ScopeManager
    0.72
    居然
    0.68
     malah
    0.68
     Somehow
    0.66
     yet
    0.64
    竟然
    0.60
    却
    0.60
     instead
    0.60
    Somehow
    0.60
    Act Density 0.106%

    No Known Activations